linux-kernel - [PATCH v2 07/10] riscv: Improve amoswap.X use in xchg()

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date: Wed, 26 Jun 2024 15:03:44 +0200
From: Alexandre Ghiti <alexghiti@...osinc.com>
To: Jonathan Corbet <corbet@....net>,
	Paul Walmsley <paul.walmsley@...ive.com>,
	Palmer Dabbelt <palmer@...belt.com>,
	Albert Ou <aou@...s.berkeley.edu>,
	Andrea Parri <parri.andrea@...il.com>,
	Nathan Chancellor <nathan@...nel.org>,
	Peter Zijlstra <peterz@...radead.org>,
	Ingo Molnar <mingo@...hat.com>,
	Will Deacon <will@...nel.org>,
	Waiman Long <longman@...hat.com>,
	Boqun Feng <boqun.feng@...il.com>,
	Arnd Bergmann <arnd@...db.de>,
	Leonardo Bras <leobras@...hat.com>,
	Guo Ren <guoren@...nel.org>,
	linux-doc@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	linux-riscv@...ts.infradead.org,
	linux-arch@...r.kernel.org
Cc: Alexandre Ghiti <alexghiti@...osinc.com>,
	Andrea Parri <andrea@...osinc.com>
Subject: [PATCH v2 07/10] riscv: Improve amoswap.X use in xchg()

xchg() uses amoswap.X instructions from Zabha but still uses
the LR/SC acquire/release semantics which require barriers.

Let's improve that by using proper amoswap acquire/release semantics in
order to avoid any of those barriers.

Suggested-by: Andrea Parri <andrea@...osinc.com>
Signed-off-by: Alexandre Ghiti <alexghiti@...osinc.com>
---
 arch/riscv/include/asm/cmpxchg.h | 35 +++++++++++++-------------------
 1 file changed, 14 insertions(+), 21 deletions(-)

diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index eb35e2d30a97..0e57d5fbf227 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -11,8 +11,8 @@
 #include <asm/fence.h>
 #include <asm/alternative.h>
 
-#define __arch_xchg_masked(sc_sfx, swap_sfx, prepend, sc_append,	\
-			   swap_append, r, p, n)			\
+#define __arch_xchg_masked(sc_sfx, swap_sfx, sc_prepend, sc_append,	\
+			   r, p, n)					\
 ({									\
 	__label__ zabha, end;						\
 									\
@@ -31,7 +31,7 @@
 	ulong __rc;							\
 									\
 	__asm__ __volatile__ (						\
-	       prepend							\
+	       sc_prepend							\
 	       "0:	lr.w %0, %2\n"					\
 	       "	and  %1, %0, %z4\n"				\
 	       "	or   %1, %1, %z3\n"				\
@@ -48,9 +48,7 @@
 zabha:									\
 	if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA)) {			\
 		__asm__ __volatile__ (					\
-			prepend						\
 			"	amoswap" swap_sfx " %0, %z2, %1\n"	\
-			swap_append						\
 			: "=&r" (r), "+A" (*(p))			\
 			: "rJ" (n)					\
 			: "memory");					\
@@ -58,19 +56,17 @@ zabha:									\
 end:;									\
 })
 
-#define __arch_xchg(sfx, prepend, append, r, p, n)			\
+#define __arch_xchg(sfx, r, p, n)					\
 ({									\
 	__asm__ __volatile__ (						\
-		prepend							\
 		"	amoswap" sfx " %0, %2, %1\n"			\
-		append							\
 		: "=r" (r), "+A" (*(p))					\
 		: "r" (n)						\
 		: "memory");						\
 })
 
-#define _arch_xchg(ptr, new, sc_sfx, swap_sfx, prepend,			\
-		   sc_append, swap_append)				\
+#define _arch_xchg(ptr, new, sc_sfx, swap_sfx,				\
+		   sc_prepend, sc_append)				\
 ({									\
 	__typeof__(ptr) __ptr = (ptr);					\
 	__typeof__(*(__ptr)) __new = (new);				\
@@ -79,21 +75,19 @@ end:;									\
 	switch (sizeof(*__ptr)) {					\
 	case 1:								\
 		__arch_xchg_masked(sc_sfx, ".b" swap_sfx,		\
-				   prepend, sc_append, swap_append,	\
+				   sc_prepend, sc_append,		\
 				   __ret, __ptr, __new);		\
 		break;							\
 	case 2:								\
 		__arch_xchg_masked(sc_sfx, ".h" swap_sfx,		\
-				   prepend, sc_append, swap_append,	\
+				   sc_prepend, sc_append,		\
 				   __ret, __ptr, __new);		\
 		break;							\
 	case 4:								\
-		__arch_xchg(".w" swap_sfx, prepend, swap_append,	\
-			      __ret, __ptr, __new);			\
+		__arch_xchg(".w" swap_sfx,  __ret, __ptr, __new);	\
 		break;							\
 	case 8:								\
-		__arch_xchg(".d" swap_sfx, prepend, swap_append,	\
-			      __ret, __ptr, __new);			\
+		__arch_xchg(".d" swap_sfx,  __ret, __ptr, __new);	\
 		break;							\
 	default:							\
 		BUILD_BUG();						\
@@ -102,17 +96,16 @@ end:;									\
 })
 
 #define arch_xchg_relaxed(ptr, x)					\
-	_arch_xchg(ptr, x, "", "", "", "", "")
+	_arch_xchg(ptr, x, "", "", "", "")
 
 #define arch_xchg_acquire(ptr, x)					\
-	_arch_xchg(ptr, x, "", "", "",					\
-		   RISCV_ACQUIRE_BARRIER, RISCV_ACQUIRE_BARRIER)
+	_arch_xchg(ptr, x, "", ".aq", "", RISCV_ACQUIRE_BARRIER)
 
 #define arch_xchg_release(ptr, x)					\
-	_arch_xchg(ptr, x, "", "", RISCV_RELEASE_BARRIER, "", "")
+	_arch_xchg(ptr, x, "", ".rl", RISCV_RELEASE_BARRIER, "")
 
 #define arch_xchg(ptr, x)						\
-	_arch_xchg(ptr, x, ".rl", ".aqrl", "", RISCV_FULL_BARRIER, "")
+	_arch_xchg(ptr, x, ".rl", ".aqrl", "", RISCV_FULL_BARRIER)
 
 #define xchg32(ptr, x)							\
 ({									\
-- 
2.39.2